Classification of Arabic Documents by a Model of Fuzzy Proximity with a Radial Basis Function

In this paper we propose a model of classification based on the principle of the fuzzy proximity of the terms within the documents. Given the heterogeneous nature of the Arabic documents in our possession, we have studied for this purpose the research model based on the semantic proximity of terms and inspired from the classic Boolean model. Our approach is based on the assumption that more the occurrences of terms in query are close with good connectivity in the extracted semantic graph from the set of document , more this document is relevant to this query. We propose a measure that provides a contextual and semantic search. We used not only a semantic graph to highlight the semantic connections between terms, but also an auxiliary dictionary to increase the connectivity of the graph and therefore the discrimination of documents relevant to the query.